CN112067625A - Device and method for detecting surface defects of rubber ring parting line - Google Patents
Device and method for detecting surface defects of rubber ring parting line Download PDFInfo
- Publication number
- CN112067625A CN112067625A CN202011011158.0A CN202011011158A CN112067625A CN 112067625 A CN112067625 A CN 112067625A CN 202011011158 A CN202011011158 A CN 202011011158A CN 112067625 A CN112067625 A CN 112067625A
- Authority
- CN
- China
- Prior art keywords
- rubber ring
- parting line
- reflector
- lower edge
- defect
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8858—Flaw counting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8861—Determining coordinates of flaws
- G01N2021/8864—Mapping zones of defects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a device and a method for detecting surface defects of a parting line of a rubber ring, wherein the device mainly comprises a green light source module, a red light source module, a first acquisition module, a second acquisition module, a first reflector group, a second reflector group and a transparent glass plate, and surface images of all positions in a 360-degree circumference at the parting line at the inner side and the outer side of the rubber ring are acquired; the method mainly comprises the steps of analyzing the intensity values of red, green and blue in RGB three channels in a surface image at a parting line of a rubber ring to obtain intensity change curves of three colors, and determining the defect position through the intersection point of the curves of the three colors. Through the mode, the rubber ring defect detection can be efficiently, quickly and accurately realized.
Description
Technical Field
The invention relates to the field of rubber ring defect detection, in particular to a device and a method for detecting surface defects of a rubber ring parting line.
Background
In the production process of the rubber ring, the parting surface of the rubber ring is easy to have defects due to reasons such as template separation and the like. Flash, edge deletion, die opening shrinkage crack, pits and the like are common defects and are defects to be avoided as much as possible for the rubber ring. At present, many manufacturers still adopt a manual detection mode, and a human eye detection method has no fixed detection mode and is easy to miss detection; and human eye detection cost is high, efficiency is low, degree of automation is low, and the method is not suitable for detecting a large number of rubber rings. In order to improve the detection efficiency, Chinese patent CN103712989B discloses a method for detecting the appearance defects of an O-shaped rubber ring, which is based on the principle that the visual effect of worker detection is improved and the visual fatigue is relieved by controlling the strength and the direction of a fluorescent lamp and the color of a plastic plate. In order to realize industrial automation, liberate labor force and improve efficiency, the method of machine vision can realize the rapid detection of the rubber ring defects and fundamentally realize the efficient, rapid and accurate detection of the rubber ring defects.
Disclosure of Invention
The invention aims to overcome the defects of low manual detection efficiency, high cost and the like in the prior art, and provides a device and a method for detecting the surface defects of a rubber ring parting line, which have the advantages of high efficiency, rapidness, accuracy and the like.
The invention realizes the purpose through the following technical scheme:
the invention relates to a device for detecting surface defects of a rubber ring parting line, which consists of a green light source module, a red light source module, a first acquisition module, a second acquisition module, a first reflector group, a second reflector group and a transparent glass plate;
the rubber ring to be detected is horizontally placed on the transparent glass, the transparent glass plate is taken as a reference surface, the green light source module and the red light source module are arranged on two sides of the transparent glass plate in the vertical direction, the light outlet holes of the two light source modules are opposite, and the first reflector group and the second reflector group are arranged at different spatial plane positions above the transparent glass plate; the first collection module is arranged at the position of a spatial plane above the first reflector set, and the second reflector set is arranged at the position of a spatial plane above the second collection module.
The green light source module consists of an annularly distributed green light source and a diffusion curved surface, the diffusion curved surface is a space curved surface structure coated with scattering paint, green light generated by the green light source is reflected by the diffusion curved surface and then presents uniform green circular light spots on the opposite transparent glass, and the diameter of each light spot is larger than that of the rubber ring to be detected;
the red light source module consists of an annularly distributed red light source and a diffusion curved surface, the diffusion curved surface is coated with a scattering coating space curved surface structure, red light generated by the red light source is reflected by the diffusion curved surface and then presents uniform red round light spots on the opposite transparent glass, and the diameter of each light spot is larger than that of the rubber ring to be detected; the green light spot and the red light spot keep the circle center on the same vertical line on the surface of the transparent glass plate.
The first reflector group is composed of a plurality of reflectors which are uniformly distributed on the circumference of the same horizontal height, the installation angle of each reflector enables the rubber ring outer side parting line to be observed from the emergent direction of the reflector, and all positions of the rubber ring outer side parting line can be covered by combining the observation of all reflector emergent directions of the reflector group.
The second reflector group is composed of a plurality of reflectors which are uniformly distributed on the circumference of the same horizontal height, the installation angle of each reflector enables the rubber ring inner side parting line to be observed from the emergent direction of the reflector group, and all positions of the rubber ring inner side parting line can be covered by combining the observation of all reflector emergent directions of the reflector group.
The first collecting module is composed of a plurality of collecting assemblies which are uniformly and circumferentially distributed on the same horizontal height and have the same number with the reflectors in the first reflector group, and each collecting assembly is composed of a camera and a lens. Each collecting assembly is aligned with one reflector of the first reflector group to be matched with the reflector for image collection, and the optical axis of each assembly lens is parallel to the central line of the emergent direction of the corresponding reflector and is superposed;
the second acquisition module is composed of a plurality of acquisition components which are uniformly and circumferentially distributed on the same horizontal height and have the same number with the reflectors in the second reflector group, and each acquisition component is composed of a camera and a lens. Each acquisition assembly is matched with one reflector of the second reflector group for image acquisition, and the optical axis of each assembly lens is parallel to the central line of the emergent direction of the corresponding reflector and is superposed;
a method for detecting surface defects of a rubber ring parting line comprises the following steps:
s1: performing graying processing on surface images at parting lines on the inner side and the outer side of the rubber ring to obtain a grayscale image at the parting line of the rubber ring;
s2: carrying out Laplace difference on the gray level image at the parting line of the rubber ring to obtain a difference image at the parting line of the rubber ring;
s3: carrying out self-adaptive binarization processing on the surface difference image at the parting line of the rubber ring to obtain a surface binary image at the parting line of the rubber ring;
s4: acquiring the upper edge and the lower edge of a rubber ring part in a surface binary image at a parting line of the rubber ring; recording the coordinates of each pixel forming the upper edge of the rubber ring part as a coordinate set of the upper edge point of the surface binary image at the parting line of the rubber ring; recording the coordinates of each pixel forming the lower edge of the rubber ring part as a coordinate set of the lower edge point of the surface binary image at the parting line of the rubber ring;
s5: performing quadratic polynomial fitting by taking the abscissa of the coordinate set of the upper edge point as an independent variable and taking the ordinate as a dependent variable to obtain the fitted ordinate; forming a coordinate set of the reference upper edge point by the abscissa of the coordinate set of the upper edge point and the fitted corresponding ordinate; performing quadratic polynomial fitting by taking the abscissa of the coordinate set of the lower edge point as an independent variable and taking the ordinate as a dependent variable to obtain the fitted ordinate; the coordinate set of the preferable lower edge point is formed by the abscissa of the coordinate set of the lower edge point and the fitted corresponding ordinate;
s6: according to the coordinate set of the preferable lower edge points, obtaining the intensity values of red, green and blue in RGB three channels in the surface image of the coordinates of each preferable lower edge point at the parting line of the rubber ring to obtain an intensity curve of three colors of the preferable lower edge points, wherein the abscissa of the preferable lower edge points is taken as the horizontal axis, and the intensity value of the preferable lower edge points corresponding to the RGB three channels is taken as the vertical axis; drawing intensity curves of the three colors in the same coordinate system to obtain a three-color intensity curve graph;
s7: according to the intensity curve graph of the preferred lower edge point with three colors, finding and recording intersection points of the intensity curves of the three colors in the curve graph, determining points between coordinates of adjacent intersection points as defect points, and recording the coordinates corresponding to the defect points as a defect point coordinate set;
s8: judging whether the preferable lower edge point coordinate set and the reference upper edge point coordinate set have intersection points or not, and if the intersection points exist, entering the ninth operation; if the intersection point does not exist, the horizontal coordinate is unchanged, the vertical coordinate in all the preferable lower edge point coordinate sets is reduced by a coordinate division value of 1 unit to form a new preferable lower edge point set, the operation is substituted into the operation of the step six, and the iterative operation of the step six, the step seven and the step eight is carried out until the intersection point exists between the new preferable lower edge point set and the reference upper edge point;
s9: drawing a preliminary defect binary image according to all the defect point coordinate sets;
s10: performing connected domain analysis on the preliminary defect binary image to obtain the area, position and number of the connected domains of the defect binary image, and screening and reserving the connected domains with the areas larger than the control threshold value to form a surface defect image at the parting line of the rubber ring;
s11: performing the first to tenth steps on the surface images of the positions in the 360-degree circumference of the inner and outer parting lines of the rubber ring to obtain surface defect images of the positions in the 360-degree circumference of the inner and outer parting lines of the rubber ring; and counting the sum of the total number of defects and the area of the surface defect image at each position in the 360-degree circumference of the parting line on the inner side and the outer side of the rubber ring, wherein when the number of the defects is greater than the defect number control threshold or the area is greater than the defect area control threshold, the surface at the parting line of the rubber ring is indicated to have defects.
A method for detecting the surface defects of the parting lines of the rubber ring is applied to surface images of all positions in the 360-degree circumference at the parting lines on the inner side and the outer side of the rubber ring, which are obtained by a device for detecting the surface defects of the parting lines of the rubber ring, and the surface images are processed and analyzed.
The invention has the beneficial effects that:
the invention relates to a device and a method for detecting surface defects of a rubber ring parting line, which are characterized in that compared with the prior art, the device and the method have the advantages that a novel illumination method is adopted to obtain surface images of the rubber ring parting line, intensity change information of three colors of the images is respectively obtained, and defect points are searched; finally, traversing the whole picture to obtain all defect points, and finally judging the surface information of the parting line of the tested rubber ring; therefore, the defect information of the rubber ring parting line surface image can be extracted quickly and efficiently.
Drawings
FIG. 1 is a schematic perspective view of an embodiment of a device for detecting surface defects of a parting line of a rubber ring according to the present invention;
FIG. 2 is a schematic front view of an embodiment of an apparatus for detecting surface defects of a parting line of a rubber ring according to the present invention;
FIG. 3 is a schematic top sectional view of an embodiment of an apparatus for detecting surface defects of a parting line of a rubber ring according to the present invention;
FIG. 4 is a schematic view of a lower section of an embodiment of the apparatus for detecting surface defects of a parting line of a rubber ring according to the present invention;
FIG. 5 is a schematic view of a block diagram of an embodiment of an apparatus for detecting surface defects of a parting line of a rubber ring according to the present invention;
FIG. 6 is a rubber ring parting line surface image of a rubber ring used in an embodiment of the present invention;
FIG. 7 is a graph of the variation of a defect-containing three-color curve used in an embodiment of the present invention;
FIG. 8 is a graph of the variation of the curves for three colors without defects, as used in an embodiment of the present invention;
fig. 9 is a defect diagram of a rubber ring parting line surface image of a rubber ring used in an embodiment of the present invention.
In the figure: 11. a first camera; 12. a second camera; 13. a third camera; 14. a fourth camera; 15. a fifth camera; 16. a camera six; 21. a seventh camera; 22. a camera eight; 23. a ninth camera; 24. ten cameras; 25. eleven cameras; 26. a camera twelve; 31. a first lens; 32. a second lens; 33. a third lens; 34. a fourth lens; 35. a fifth lens; 36. a sixth lens; 41. a seventh lens; 42. a lens eighth; 43. a ninth lens; 44. a lens ten; 45. eleven lenses; 46. a twelfth lens; 51. a green light source module; 61. a first reflecting mirror; 62. a second reflecting mirror; 63. a third reflector; 64. a fourth reflecting mirror; 65. a fifth reflecting mirror; 66. a sixth reflector; 71. a seventh reflecting mirror; 72. a reflector eight; 73. a ninth reflecting mirror; 74. a reflector ten; 75. eleven reflectors; 76. a mirror twelve; 81. a rubber ring; 91. a transparent glass plate; 100. a red light source module; 10. a first camera set; 40. a first lens group; 140. a first acquisition module; 20. a second camera set; 30. a second lens group; 230. a second acquisition module; 70. a first reflector group; 60. a second mirror group.
Detailed Description
The invention will be further described with reference to the accompanying drawings in which:
as shown in fig. 1-9: the device consists of a green light source module 510, a red light source module 100, a first acquisition module 230, a second acquisition module 140, a first reflector set 70, a second reflector set 60 and a transparent glass plate 91;
the detected rubber ring 81 is horizontally placed on the transparent glass 91, the transparent glass plate 91 is taken as a reference surface, the green light source module 510 and the red light source module 100 are installed at two sides of the transparent glass plate 91 in the vertical direction, the light outlet positions of the two light source modules are kept opposite, and the first reflector group 70 and the second reflector group 60 are installed at different spatial plane positions above the transparent glass plate 91; the first collection module 230 is mounted above the first mirror set 70 and the second mirror set 60 is mounted above the second collection module 140.
The green light source module 510 is composed of an annularly distributed green light source and a diffusion curved surface, the diffusion curved surface is coated with a scattering coating space curved surface structure, green light generated by the green light source is reflected by the diffusion curved surface, uniform green circular light spots are displayed on the transparent glass 91 which is opposite to the green light source, and the diameter of each light spot is larger than that of the rubber ring 81 to be detected;
the red light source module 100 consists of an annularly distributed red light source and a diffusion curved surface, the diffusion curved surface is coated with a scattering coating space curved surface structure, red light generated by the red light source is reflected by the diffusion curved surface and then presents uniform red round light spots on the opposite transparent glass, and the diameter of each light spot is larger than that of the rubber ring 81 to be detected; the green and red spots remain centered on the same vertical line on the surface of the transparent glass sheet 91.
The first reflector group 70 is composed of 6 reflectors 71, 72, 73, 74, 75 and 76 which are circumferentially distributed on the same horizontal height, the installation angle of each reflector ensures that the outgoing direction of the reflector can observe the outer side parting line of the rubber ring 81, and each position of the outer side parting line of the rubber ring 81 can be observed by combining a seventh reflector 71, an eighth reflector 72, a ninth reflector 73, a tenth reflector 74, an eleventh reflector 75 and a twelfth reflector 76;
the second reflector group 60 is composed of 6 reflectors 61, 62, 63, 64, 65 and 66 which are circumferentially and uniformly distributed on the same horizontal height, the installation angle of each reflector is to ensure that the emergent direction of the reflector can observe the parting line on the inner side of the rubber ring 81, and each position of the parting line on the inner side of the rubber ring 81 can be observed by combining 6 reflectors 61, two reflectors 62, three reflectors 63, four reflectors 64, five reflectors 65 and six reflectors 66;
the first collecting module 230 is composed of camera groups 20 which are uniformly distributed on the same horizontal height in a circumferential manner and have the same number as the first reflecting mirror group 70, installation modules which comprise a camera seventh 21, a camera eighth 22, a camera ninth 23, a camera tenth 24, a camera eleventh 25, a camera twelfth 26 and a lens group 30, a lens seventh 21, a lens seventh 32, a lens seventh 33, a lens sixth 34, a lens fifth 35 and a lens sixth 36, a camera seventh 21, a camera eighth 22 and a camera ninth 23, mounting assemblies of a camera ten 24, a camera eleven 25, a camera twelve 26, a lens one 31, a lens two 32, a lens three 33, a lens four 34, a lens five 35 and a lens six 36 are all aligned with a reflector seven 71, a reflector eight 72, a reflector nine 73, a reflector ten 74, a reflector eleven 75 and a reflector twelve 76 of the first reflector group 70 one by one, and the optical axis of each lens is parallel to the central line of the emergent direction of the corresponding reflector;
the second collecting module 140 is composed of camera groups 10 which are uniformly distributed on the same horizontal height in a circumferential manner and have the same number as the second reflecting mirror groups 60, and installation modules which comprise a first camera 11, a second camera 12, a third camera 13, a fourth camera 14, a fifth camera 15, a twelfth camera 26, a sixth lens group 40, a seventh lens 46, an eighth lens 41, a ninth lens 42, a tenth lens 43, an eleventh lens 44 and a twelfth lens 45, the first camera 11, the second camera 12 and the third camera 13, mounting components of a camera four 14, a camera five 15, a camera twelve 26, a lens seven 46, a lens eight 41, a lens nine 42, a lens ten 43, a lens eleven 44 and a lens twelve 45 are all aligned with a corresponding reflector one 61, a reflector two 62, a reflector three 63, a reflector four 64, a reflector five 65 and a reflector six 66 of the second reflector group 60 one by one, and the optical axis of each lens is parallel to and coincident with the central line of the emergent direction of the corresponding reflector;
a method for detecting surface defects of a rubber ring parting line comprises the following steps:
s1: performing graying processing on surface images at parting lines on the inner side and the outer side of the rubber ring to obtain a grayscale image at the parting line of the rubber ring; FIG. 6 schematically illustrates a rubber ring parting line surface image acquired using an apparatus for rubber ring parting line surface defect detection;
s2: carrying out Laplace difference on the gray level image at the parting line of the rubber ring to obtain a difference image at the parting line of the rubber ring;
s3: carrying out self-adaptive binarization processing on the surface difference image at the parting line of the rubber ring to obtain a surface binary image at the parting line of the rubber ring;
s4: acquiring the upper edge and the lower edge of a rubber ring part in a surface binary image at a parting line of the rubber ring; recording the coordinates of each pixel forming the upper edge of the rubber ring part as a coordinate set of the upper edge point of the surface binary image at the parting line of the rubber ring; recording the coordinates of each pixel forming the lower edge of the rubber ring part as a coordinate set of the lower edge point of the surface binary image at the parting line of the rubber ring;
s5: performing quadratic polynomial fitting by taking the abscissa of the coordinate set of the upper edge point as an independent variable and taking the ordinate as a dependent variable to obtain the fitted ordinate; forming a coordinate set of the reference upper edge point by the abscissa of the coordinate set of the upper edge point and the fitted corresponding ordinate; performing quadratic polynomial fitting by taking the abscissa of the coordinate set of the lower edge point as an independent variable and taking the ordinate as a dependent variable to obtain the fitted ordinate; the coordinate set of the preferable lower edge point is formed by the abscissa of the coordinate set of the lower edge point and the fitted corresponding ordinate;
the quadratic polynomial fitting adopts Ceres solution which is an open source C + + library and is used for modeling and solving large-scale complex optimization problems. The least squares problem solved with Ceres is most general in the form (bounded kernel least squares):
s.t. lj＜xj＜uj (2)
ρirepresenting a loss function, pi(||fi(xi1，…xik)||2) Representing a residual block, x representing the abscissa of the coordinates of the lower edge point, and y representing the ordinate of the coordinates of the lower edge point.
An objective function: y is ax2+ bx + c. Using least square method, iterative operation to make quadratic polynomial fitting and obtain three parameters of a, b and c。
S6: according to the coordinate set of the preferable lower edge points, obtaining the intensity values of red, green and blue in RGB three channels in the surface image of the coordinates of each preferable lower edge point at the parting line of the rubber ring to obtain an intensity curve of three colors of the preferable lower edge points, wherein the abscissa of the preferable lower edge points is taken as the horizontal axis, and the intensity value of the preferable lower edge points corresponding to the RGB three channels is taken as the vertical axis; drawing intensity curves of the three colors in the same coordinate system to obtain a three-color intensity curve graph;
s7: according to the intensity curve graph of the preferred lower edge point with three colors, finding and recording intersection points of the intensity curves of the three colors in the curve graph, determining points between coordinates of adjacent intersection points as defect points, and recording the coordinates corresponding to the defect points as a defect point coordinate set; FIG. 7 is a schematic representation of a three color intensity curve variation plot in the presence of a defect point, the intersection of the three color intensity curves as the lower edge crosses the defect location; FIG. 8 is a schematic representation of a three color intensity profile variation without defect points, where the three color intensity profiles do not intersect when the lower edge is drawn across a defect-free location;
s8: judging whether the preferable lower edge point coordinate set and the reference upper edge point coordinate set have intersection points or not, and if the intersection points exist, entering the ninth operation; if the intersection point does not exist, the horizontal coordinate is unchanged, the vertical coordinate in all the preferable lower edge point coordinate sets is reduced by a coordinate division value of 1 unit to form a new preferable lower edge point set, the operation is substituted into the operation of the step six, and the iterative operation of the step six, the step seven and the step eight is carried out until the intersection point exists between the new preferable lower edge point set and the reference upper edge point;
s9: drawing a preliminary defect binary image according to all the defect point coordinate sets;
s10: performing connected domain analysis on the preliminary defect binary image to obtain the area, position and number of the connected domains of the defect binary image, and screening and reserving the connected domains with the areas larger than the control threshold value to form a surface defect image at the parting line of the rubber ring; fig. 9 schematically shows a defect map extracted from the rubber ring parting line surface image, and white portions are defects.
S11: performing the first to tenth steps on the surface images of the positions in the 360-degree circumference of the inner and outer parting lines of the rubber ring to obtain surface defect images of the positions in the 360-degree circumference of the inner and outer parting lines of the rubber ring; and counting the sum of the total number of defects and the area of the surface defect image at each position in the 360-degree circumference of the parting line on the inner side and the outer side of the rubber ring, wherein when the number of the defects is greater than the defect number control threshold or the area is greater than the defect area control threshold, the surface at the parting line of the rubber ring is indicated to have defects.
A method for detecting the surface defects of a parting line of a rubber ring is applied to surface images of all positions in a 360-degree circumference at the parting line at the inner side and the outer side of the rubber ring obtained by a device for detecting the defects of the parting line of the rubber ring, and each surface image is processed.
The foregoing shows and describes the general principles and features of the present invention, together with the advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. The utility model provides a device that rubber circle parting line surface defect detected for obtain the surface image of rubber circle inside and outside parting line department, its characterized in that: the device comprises a green light source module, a red light source module, a first acquisition module, a second acquisition module, a first reflector group, a second reflector group and a transparent glass plate; the rubber ring to be detected is horizontally placed on the transparent glass, the transparent glass plate is taken as a reference surface, the green light source module and the red light source module are arranged on two sides of the transparent glass plate in the vertical direction, the light outlet holes of the two light source modules are opposite, and the first reflector group and the second reflector group are arranged at different spatial plane positions above the transparent glass plate; the first collection module is arranged at the position of a spatial plane above the first reflector set, and the second reflector set is arranged at the position of a spatial plane above the second collection module.
2. The apparatus for detecting surface defects of a rubber ring parting line according to claim 1, wherein: the green light source module is composed of an annularly distributed green light source and a diffusion curved surface, the diffusion curved surface is a space curved surface structure coated with scattering paint, green light generated by the green light source is reflected by the diffusion curved surface and then shows uniform green circular light spots on the opposite transparent glass, and the diameter of each light spot is larger than that of the rubber ring to be detected.
3. The apparatus for detecting surface defects of a rubber ring parting line according to claim 1, wherein: the red light source module consists of an annularly distributed red light source and a diffusion curved surface, the diffusion curved surface is coated with a scattering coating space curved surface structure, red light generated by the red light source is reflected by the diffusion curved surface and then presents uniform red round light spots on the opposite transparent glass, and the diameter of each light spot is larger than that of the rubber ring to be detected; the green light spot and the red light spot keep the circle center on the same vertical line on the surface of the transparent glass plate.
4. The apparatus for detecting surface defects of a rubber ring parting line according to claim 1, wherein: the first reflector group is composed of a plurality of reflectors which are uniformly distributed on the circumference of the same horizontal height, the installation angle of each reflector enables the rubber ring outer side parting line to be observed from the emergent direction of the reflector, and all positions of the rubber ring outer side parting line can be covered by combining the observation of all reflector emergent directions of the reflector group.
5. The apparatus for detecting surface defects of a rubber ring parting line according to claim 1, wherein: the second reflector group is composed of a plurality of reflectors which are uniformly distributed on the circumference of the second reflector group at the same horizontal height, the installation angle of each reflector enables the rubber ring inner side parting line to be observed from the emergent direction of the reflector group, and all positions of the rubber ring inner side parting line can be covered by combining the observation of all reflector emergent directions of the reflector group.
6. The apparatus for detecting surface defects of a rubber ring parting line according to claim 1, wherein: the first collecting module is composed of a plurality of collecting assemblies which are uniformly and circumferentially distributed on the same horizontal height and have the same number with the reflectors in the first reflector group, and each collecting assembly is composed of a camera and a lens. Each collecting assembly is aligned with one reflector of the first reflector group to be matched with the first reflector group for image collection, and the optical axis of each assembly lens is parallel to the central line of the emergent direction of the corresponding reflector and is superposed.
7. The apparatus for detecting surface defects of a rubber ring parting line according to claim 1, wherein: the second acquisition module is composed of a plurality of acquisition components which are uniformly and circumferentially distributed on the same horizontal height and have the same number with the reflectors in the second reflector group, and each acquisition component is composed of a camera and a lens. Each collecting assembly is matched with one reflector of the second reflector group for image collection, and the optical axis of each assembly lens is parallel to the central line of the emergent direction of the corresponding reflector and is superposed.
8. A method for detecting surface defects of a rubber ring parting line is characterized by comprising the following steps: the method comprises the following steps:
s1: performing graying processing on surface images at parting lines on the inner side and the outer side of the rubber ring to obtain a grayscale image at the parting line of the rubber ring;
s2: carrying out Laplace difference on the gray level image at the parting line of the rubber ring to obtain a difference image at the parting line of the rubber ring;
s3: carrying out self-adaptive binarization processing on the surface difference image at the parting line of the rubber ring to obtain a surface binary image at the parting line of the rubber ring;
s4: acquiring the upper edge and the lower edge of a rubber ring part in a surface binary image at a parting line of the rubber ring; recording the coordinates of each pixel forming the upper edge of the rubber ring part as a coordinate set of the upper edge point of the surface binary image at the parting line of the rubber ring; recording the coordinates of each pixel forming the lower edge of the rubber ring part as a coordinate set of the lower edge point of the surface binary image at the parting line of the rubber ring;
s5: performing quadratic polynomial fitting by taking the abscissa of the coordinate set of the upper edge point as an independent variable and taking the ordinate as a dependent variable to obtain the fitted ordinate; forming a coordinate set of the reference upper edge point by the abscissa of the coordinate set of the upper edge point and the fitted corresponding ordinate; performing quadratic polynomial fitting by taking the abscissa of the coordinate set of the lower edge point as an independent variable and taking the ordinate as a dependent variable to obtain the fitted ordinate; the coordinate set of the preferable lower edge point is formed by the abscissa of the coordinate set of the lower edge point and the fitted corresponding ordinate;
s6: according to the coordinate set of the preferable lower edge points, obtaining the intensity values of red, green and blue in RGB three channels in the surface image of the coordinates of each preferable lower edge point at the parting line of the rubber ring to obtain an intensity curve of three colors of the preferable lower edge points, wherein the abscissa of the preferable lower edge points is taken as the horizontal axis, and the intensity value of the preferable lower edge points corresponding to the RGB three channels is taken as the vertical axis; drawing intensity curves of the three colors in the same coordinate system to obtain a three-color intensity curve graph;
s7: according to the intensity curve graph of the preferred lower edge point with three colors, finding and recording intersection points of the intensity curves of the three colors in the curve graph, determining points between coordinates of adjacent intersection points as defect points, and recording the coordinates corresponding to the defect points as a defect point coordinate set;
s8: judging whether the preferable lower edge point coordinate set and the reference upper edge point coordinate set have intersection points or not, and if the intersection points exist, entering the ninth operation; if the intersection point does not exist, the horizontal coordinate is unchanged, the vertical coordinate in all the preferable lower edge point coordinate sets is reduced by a coordinate division value of 1 unit to form a new preferable lower edge point set, the operation is substituted into the operation of the step six, and the iterative operation of the step six, the step seven and the step eight is carried out until the intersection point exists between the new preferable lower edge point set and the reference upper edge point;
s9: drawing a preliminary defect binary image according to all the defect point coordinate sets;
s10: performing connected domain analysis on the preliminary defect binary image to obtain the area, position and number of the connected domains of the defect binary image, and screening and reserving the connected domains with the areas larger than the control threshold value to form a surface defect image at the parting line of the rubber ring;
s11: performing the first to tenth steps on the surface images of the positions in the 360-degree circumference of the inner and outer parting lines of the rubber ring to obtain surface defect images of the positions in the 360-degree circumference of the inner and outer parting lines of the rubber ring; and counting the sum of the total number of defects and the area of the surface defect image at each position in the 360-degree circumference of the parting line on the inner side and the outer side of the rubber ring, wherein when the number of the defects is greater than the defect number control threshold or the area is greater than the defect area control threshold, the surface at the parting line of the rubber ring is indicated to have defects.
9. The application of the method for detecting the surface defects of the parting line of the rubber ring is characterized in that: the method is applied to surface images of all positions in the 360-degree circumference at the parting line positions inside and outside the rubber ring, which are obtained by a device for detecting the defects of the parting line of the rubber ring, and the images are processed and analyzed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011011158.0A CN112067625A (en) | 2020-09-23 | 2020-09-23 | Device and method for detecting surface defects of rubber ring parting line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011011158.0A CN112067625A (en) | 2020-09-23 | 2020-09-23 | Device and method for detecting surface defects of rubber ring parting line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112067625A true CN112067625A (en) | 2020-12-11 |
Family
ID=73682531
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011011158.0A Withdrawn CN112067625A (en) | 2020-09-23 | 2020-09-23 | Device and method for detecting surface defects of rubber ring parting line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112067625A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734689A (en) * | 2020-12-16 | 2021-04-30 | 广州大学 | Gasket quality detection method, system, device and storage medium |
| CN113252567A (en) * | 2021-06-08 | 2021-08-13 | 菲特（天津）检测技术有限公司 | Method, system, medium and terminal for rapidly detecting multiple defects on surface of aluminum valve plate |
-
2020
- 2020-09-23 CN CN202011011158.0A patent/CN112067625A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734689A (en) * | 2020-12-16 | 2021-04-30 | 广州大学 | Gasket quality detection method, system, device and storage medium |
| CN113252567A (en) * | 2021-06-08 | 2021-08-13 | 菲特（天津）检测技术有限公司 | Method, system, medium and terminal for rapidly detecting multiple defects on surface of aluminum valve plate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110658202B (en) | Industrial component appearance defect detection method based on deep learning | |
| TWI603074B (en) | Optical film defect detection method and system thereof | |
| KR102664258B1 (en) | Colony contrast collection | |
| CN102822867B (en) | Optical defect in detection transparent substance | |
| CN104903914B (en) | Method for defining the isolated area of interested data collection in Tissue Culture Dish | |
| CN110261410A (en) | A kind of detection device and method of glass lens defect | |
| JP2004294202A (en) | Defect detection method and device of screen | |
| CN112067625A (en) | Device and method for detecting surface defects of rubber ring parting line | |
| JP2017049974A (en) | Discriminator generator, quality determine method, and program | |
| CN105021628A (en) | Detection method for surface defects of optical fiber image inverter | |
| Kukkonen et al. | Color features for quality control in ceramic tile industry | |
| CN110910372B (en) | Deep convolutional neural network-based uniform light plate defect detection method | |
| CN114119591A (en) | Display screen picture quality detection method | |
| CN112734847A (en) | Multi-target optical fiber position accurate detection positioning system and method | |
| CN110412055A (en) | A kind of lens white haze defect inspection method based on multiple light courcess dark-ground illumination | |
| CN106872488A (en) | A kind of double surface defect visible detection methods of rapid large-area transparent substrate and device | |
| CN116091505B (en) | Automatic defect detection and classification method and system for sapphire substrate | |
| CN115620061A (en) | Hardware part defect detection method and system based on image recognition technology | |
| CN116678826A (en) | Appearance defect detection system and method based on rapid three-dimensional reconstruction | |
| CN109544513A (en) | A kind of steel pipe end surface defect extraction knowledge method for distinguishing | |
| CN106683135A (en) | Method for searching optic center of lens | |
| CN109945842B (en) | Method for detecting label missing and analyzing labeling error of end face of bundled round steel | |
| CN210664378U (en) | Customized light source roughness detection device based on red-green chromatic aberration | |
| CN113808104A (en) | Block-based metal surface defect detection method and system | |
| CN107248151A (en) | A kind of LCD panel intelligent detecting method and system based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201211 |